Agentic skills for professional developer workflows — structured 1:1s, git-aware reviews, and action tracking. Works with Claude Code, Cursor, Codex, and more.
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude CodeCodex
Structured 1:1 professional check-in between the AI assistant and the user. Invoke with /1on1. The AI prepares from git history and past reviews, conducts a guided interview one question at a time, self-reflects honestly, persists action items to the agent config file, and delivers a written report.